2f397010b86c77dab0fdb4258c39c58466ed3f0da1ffc2b6a7d09336ada3577e

README.md

@@ -0,0 +1,186 @@
+---
+language:
+- code
+license: llama2
+pipeline_tag: text-generation
+tags:
+- facebook
+- meta
+- pytorch
+- llama
+- llama-2
+- mlx
+extra_gated_heading: You need to share contact information with Meta to access this
+  model
+extra_gated_prompt: "### LLAMA 2 COMMUNITY LICENSE AGREEMENT\n\"Agreement\" means\
+  \ the terms and conditions for use, reproduction, distribution and  modification\
+  \ of the Llama Materials set forth herein.  \"Documentation\" means the specifications,\
+  \ manuals and documentation  accompanying Llama 2 distributed by Meta at https://ai.meta.com/resources/models-and-libraries/llama-downloads/.\
+  \   \"Licensee\" or \"you\" means you, or your employer or any other person or entity\
+  \ (if you are entering into this Agreement on such person or entity's behalf), of\
+  \ the age required under applicable laws, rules or regulations to provide legal\
+  \ consent and that has legal authority to bind your employer or such other person\
+  \ or  entity if you are  entering in this Agreement on their behalf.  \"Llama 2\"\
+  \ means the foundational large language models and software and algorithms, including\
+  \ machine-learning model code, trained model weights, inference-enabling code, training-enabling\
+  \ code, fine-tuning enabling code and other  elements of the foregoing distributed\
+  \ by Meta at ai.meta.com/resources/models-and-libraries/llama-downloads/. \"Llama\
+  \ Materials\" means, collectively, Meta's proprietary Llama 2 and documentation\
+  \ (and any portion thereof) made available under this Agreement. \"Meta\" or \"\
+  we\" means Meta Platforms Ireland Limited (if you are located in or, if you are\
+  \ an entity, your principal place of business is in the EEA or Switzerland) and\
+  \ Meta Platforms, Inc. (if you are located outside of the EEA or Switzerland). \
+  \ By clicking \"I Accept\" below or by using or distributing any portion or element\
+  \ of the Llama Materials, you agree to be bound by this Agreement. 1. License Rights\
+  \ and Redistribution.  a. Grant of Rights. You are granted a non-exclusive, worldwide,\
+  \ non- transferable and royalty-free limited license under Meta's intellectual property\
+  \ or  other rights owned by Meta embodied in the Llama Materials to use, reproduce,\
+  \  distribute, copy, create derivative works of, and make modifications to the Llama\
+  \  Materials.  \n   \nb. Redistribution and Use.   i. If you distribute or make\
+  \ the Llama Materials, or any derivative works  thereof, available to a third party,\
+  \ you shall provide a copy of this Agreement to such  third party.  ii.  If you\
+  \ receive Llama Materials, or any derivative works thereof, from  a Licensee as\
+  \ part of an integrated end user product, then Section 2 of this  Agreement will\
+  \ not apply to you.  iii. You must retain in all copies of the Llama Materials that\
+  \ you  distribute the following attribution notice within a \"Notice\" text file\
+  \ distributed as a  part of such copies: \"Llama 2 is licensed under the LLAMA 2\
+  \ Community License,  Copyright (c) Meta Platforms, Inc. All Rights Reserved.\"\
+  \ iv. Your use of the Llama Materials must comply with applicable laws  and regulations\
+  \ (including trade compliance laws and regulations) and adhere to the  Acceptable\
+  \ Use Policy for the Llama Materials (available at  https://ai.meta.com/llama/use-policy),\
+  \ which is hereby incorporated by reference into  this Agreement. v. You will not\
+  \ use the Llama Materials or any output or results of the  Llama Materials to improve\
+  \ any other large language model (excluding Llama 2 or  derivative works thereof).\
+  \   2. Additional Commercial Terms. If, on the Llama 2 version release date, the\
+  \  monthly active users of the products or services made available by or for Licensee,\
+  \  or Licensee's affiliates, is greater than 700 million monthly active users in\
+  \ the  preceding calendar month, you must request a license from Meta, which Meta\
+  \ may  grant to you in its sole discretion, and you are not authorized to exercise\
+  \ any of the  rights under this Agreement unless or until Meta otherwise expressly\
+  \ grants you  such rights. 3. Disclaimer of Warranty. UNLESS REQUIRED BY APPLICABLE\
+  \ LAW, THE  LLAMA MATERIALS AND ANY OUTPUT AND RESULTS THEREFROM ARE  PROVIDED ON\
+  \ AN \"AS IS\" BASIS, WITHOUT WARRANTIES OF ANY KIND,  EITHER EXPRESS OR IMPLIED,\
+  \ INCLUDING, WITHOUT LIMITATION, ANY  WARRANTIES OF TITLE, NON-INFRINGEMENT, MERCHANTABILITY,\
+  \ OR  FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE  FOR DETERMINING\
+  \ THE APPROPRIATENESS OF USING OR REDISTRIBUTING  THE LLAMA MATERIALS AND ASSUME\
+  \ ANY RISKS ASSOCIATED WITH YOUR  USE OF THE LLAMA MATERIALS AND ANY OUTPUT AND\
+  \ RESULTS. 4. Limitation of Liability. IN NO EVENT WILL META OR ITS AFFILIATES BE\
+  \  LIABLE UNDER ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, TORT,  NEGLIGENCE,\
+  \ PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS  AGREEMENT, FOR ANY LOST\
+  \ PROFITS OR ANY INDIRECT, SPECIAL,  CONSEQUENTIAL, INCIDENTAL, EXEMPLARY OR PUNITIVE\
+  \ DAMAGES, EVEN  IF META OR ITS AFFILIATES HAVE BEEN ADVISED OF THE POSSIBILITY\
+  \ OF  ANY OF THE FOREGOING. 5. Intellectual Property. a. No trademark licenses are\
+  \ granted under this Agreement, and in  connection with the Llama Materials, neither\
+  \ Meta nor Licensee may use any name  or mark owned by or associated with the other\
+  \ or any of its affiliates, except as  required for reasonable and customary use\
+  \ in describing and redistributing the  Llama Materials. b. Subject to Meta's ownership\
+  \ of Llama Materials and derivatives made by or  for Meta, with respect to any derivative\
+  \ works and modifications of the Llama  Materials that are made by you, as between\
+  \ you and Meta, you are and will be the  owner of such derivative works and modifications.\
+  \ c. If you institute litigation or other proceedings against Meta or any entity\
+  \  (including a cross-claim or counterclaim in a lawsuit) alleging that the Llama\
+  \  Materials or Llama 2 outputs or results, or any portion of any of the foregoing,\
+  \  constitutes infringement of intellectual property or other rights owned or licensable\
+  \  by you, then any licenses granted to you under this Agreement shall terminate\
+  \ as of  the date such litigation or claim is filed or instituted. You will indemnify\
+  \ and hold  harmless Meta from and against any claim by any third party arising\
+  \ out of or related  to your use or distribution of the Llama Materials. 6. Term\
+  \ and Termination. The term of this Agreement will commence upon your  acceptance\
+  \ of this Agreement or access to the Llama Materials and will continue in  full\
+  \ force and effect until terminated in accordance with the terms and conditions\
+  \  herein. Meta may terminate this Agreement if you are in breach of any term or\
+  \  condition of this Agreement. Upon termination of this Agreement, you shall delete\
+  \  and cease use of the Llama Materials. Sections 3, 4 and 7 shall survive the \
+  \ termination of this Agreement.  7. Governing Law and Jurisdiction. This Agreement\
+  \ will be governed and  construed under the laws of the State of California without\
+  \ regard to choice of law  principles, and the UN Convention on Contracts for the\
+  \ International Sale of Goods  does not apply to this Agreement. The courts of California\
+  \ shall have exclusive  jurisdiction of any dispute arising out of this Agreement.\
+  \  USE POLICY ### Llama 2 Acceptable Use Policy Meta is committed to promoting safe\
+  \ and fair use of its tools and features, including Llama 2. If you access or use\
+  \ Llama 2, you agree to this Acceptable Use Policy (“Policy”). The most recent copy\
+  \ of this policy can be found at [ai.meta.com/llama/use-policy](http://ai.meta.com/llama/use-policy).\
+  \ #### Prohibited Uses We want everyone to use Llama 2 safely and responsibly. You\
+  \ agree you will not use, or allow others to use, Llama 2 to:  1. Violate the law\
+  \ or others’ rights, including to:\n  1. Engage in, promote, generate, contribute\
+  \ to, encourage, plan, incite, or further illegal or unlawful activity or content,\
+  \ such as: \n    1. Violence or terrorism \n    2. Exploitation or harm to children,\
+  \ including the solicitation, creation, acquisition, or dissemination of child exploitative\
+  \ content or failure to report Child Sexual Abuse Material\n    3. Human trafficking,\
+  \ exploitation, and sexual violence\n    4. The illegal distribution of information\
+  \ or materials to minors, including obscene materials, or failure to employ legally\
+  \ required age-gating in connection with such information or materials.\n    5.\
+  \ Sexual solicitation\n    6. Any other criminal activity\n  2. Engage in, promote,\
+  \ incite, or facilitate the harassment, abuse, threatening, or bullying of individuals\
+  \ or groups of individuals\n  3. Engage in, promote, incite, or facilitate discrimination\
+  \ or other unlawful or harmful conduct in the provision of employment, employment\
+  \ benefits, credit, housing, other economic benefits, or other essential goods and\
+  \ services\n  4. Engage in the unauthorized or unlicensed practice of any profession\
+  \ including, but not limited to, financial, legal, medical/health, or related professional\
+  \ practices \n  5. Collect, process, disclose, generate, or infer health, demographic,\
+  \ or other sensitive personal or private information about individuals without rights\
+  \ and consents required by applicable laws\n  6. Engage in or facilitate any action\
+  \ or generate any content that infringes, misappropriates, or otherwise violates\
+  \ any third-party rights, including the outputs or results of any products or services\
+  \ using the Llama 2 Materials\n  7. Create, generate, or facilitate the creation\
+  \ of malicious code, malware, computer viruses or do anything else that could disable,\
+  \ overburden, interfere with or impair the proper working, integrity, operation\
+  \ or appearance of a website or computer system \n2. Engage in, promote, incite,\
+  \ facilitate, or assist in the planning or development of activities that present\
+  \ a risk of death or bodily harm to individuals, including use of Llama 2 related\
+  \ to the following:\n  1. Military, warfare, nuclear industries or applications,\
+  \ espionage, use for materials or activities that are subject to the International\
+  \ Traffic Arms Regulations (ITAR) maintained by the United States Department of\
+  \ State\n  2. Guns and illegal weapons (including weapon development)\n  3. Illegal\
+  \ drugs and regulated/controlled substances\n  4. Operation of critical infrastructure,\
+  \ transportation technologies, or heavy machinery\n  5. Self-harm or harm to others,\
+  \ including suicide, cutting, and eating disorders\n  6. Any content intended to\
+  \ incite or promote violence, abuse, or any infliction of bodily harm to an individual\n\
+  3. Intentionally deceive or mislead others, including use of Llama 2 related to\
+  \ the following:\n  1. Generating, promoting, or furthering fraud or the creation\
+  \ or promotion of disinformation\n  2. Generating, promoting, or furthering defamatory\
+  \ content, including the creation of defamatory statements, images, or other content\n\
+  \  3. Generating, promoting, or further distributing spam\n  4. Impersonating another\
+  \ individual without consent, authorization, or legal right\n  5. Representing that\
+  \ the use of Llama 2 or outputs are human-generated\n  6. Generating or facilitating\
+  \ false online engagement, including fake reviews and other means of fake online\
+  \ engagement \n  4. Fail to appropriately disclose to end users any known dangers\
+  \ of your AI system \nPlease report any violation of this Policy, software “bug,”\
+  \ or other problems that could lead to a violation of this Policy through one of\
+  \ the following means: * Reporting issues with the model: [github.com/facebookresearch/llama](http://github.com/facebookresearch/llama)\
+  \ * Reporting risky content generated by the model: [developers.facebook.com/llama_output_feedback](http://developers.facebook.com/llama_output_feedback)\
+  \ * Reporting bugs and security concerns: [facebook.com/whitehat/info](http://facebook.com/whitehat/info)\
+  \ * Reporting violations of the Acceptable Use Policy or unlicensed uses of Llama:\
+  \ [LlamaUseReport@meta.com](mailto:LlamaUseReport@meta.com)"
+extra_gated_fields:
+  First Name: text
+  Last Name: text
+  Date of birth: date_picker
+  Country: country
+  Affiliation: text
+  geo: ip_location
+  ? By clicking Submit below I accept the terms of the license and acknowledge that
+    the information I provide will be collected stored processed and shared in accordance
+    with the Meta Privacy Policy
+  : checkbox
+extra_gated_description: The information you provide will be collected, stored, processed
+  and shared in accordance with the [Meta Privacy Policy](https://www.facebook.com/privacy/policy/).
+extra_gated_button_content: Submit
+---
+
+# ipetrukha/CodeLlama-34b-Instruct-hf-4bit
+
+The Model [ipetrukha/CodeLlama-34b-Instruct-hf-4bit](https://huggingface.co/ipetrukha/CodeLlama-34b-Instruct-hf-4bit) was converted to MLX format from [meta-llama/CodeLlama-34b-Instruct-hf](https://huggingface.co/meta-llama/CodeLlama-34b-Instruct-hf) using mlx-lm version **0.16.1**.
+
+## Use with mlx
+
+```bash
+pip install mlx-lm
+```
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load("ipetrukha/CodeLlama-34b-Instruct-hf-4bit")
+response = generate(model, tokenizer, prompt="hello", verbose=True)
+```

added_tokens.json

@@ -0,0 +1,6 @@
+{
+  "▁<EOT>": 32003,
+  "▁<MID>": 32001,
+  "▁<PRE>": 32000,
+  "▁<SUF>": 32002
+}

config.json

@@ -0,0 +1,29 @@
+{
+    "architectures": [
+        "LlamaForCausalLM"
+    ],
+    "bos_token_id": 1,
+    "eos_token_id": 2,
+    "hidden_act": "silu",
+    "hidden_size": 8192,
+    "initializer_range": 0.02,
+    "intermediate_size": 22016,
+    "max_position_embeddings": 16384,
+    "model_type": "llama",
+    "num_attention_heads": 64,
+    "num_hidden_layers": 48,
+    "num_key_value_heads": 8,
+    "pretraining_tp": 1,
+    "quantization": {
+        "group_size": 64,
+        "bits": 4
+    },
+    "rms_norm_eps": 1e-05,
+    "rope_scaling": null,
+    "rope_theta": 1000000,
+    "tie_word_embeddings": false,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.32.0.dev0",
+    "use_cache": true,
+    "vocab_size": 32000
+}

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:468ff1658034cb7992005929a6d8796523ce9ab5f4b33c08cd341a54e55c5f9e
+size 1956312791

model.safetensors.index.json

@@ -0,0 +1,1118 @@
+{
+    "metadata": {
+        "total_size": 18982125568
+    },
+    "weight_map": {
+        "lm_head.biases": "model-00004-of-00004.safetensors",
+        "lm_head.scales": "model-00004-of-00004.safetensors",
+        "lm_head.weight": "model-00004-of-00004.safetensors",
+        "model.embed_tokens.biases": "model-00001-of-00004.safetensors",
+        "model.embed_tokens.scales": "model-00001-of-00004.safetensors",
+        "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+        "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.0.mlp.down_proj.biases": "model-00001-of-00004.safetensors",
+        "model.layers.0.mlp.down_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.0.mlp.gate_proj.biases": "model-00001-of-00004.safetensors",
+        "model.layers.0.mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.0.mlp.up_proj.biases": "model-00001-of-00004.safetensors",
+        "model.layers.0.mlp.up_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.0.self_attn.k_proj.biases": "model-00001-of-00004.safetensors",
+        "model.layers.0.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.0.self_attn.o_proj.biases": "model-00001-of-00004.safetensors",
+        "model.layers.0.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.0.self_attn.q_proj.biases": "model-00001-of-00004.safetensors",
+        "model.layers.0.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.0.self_attn.v_proj.biases": "model-00001-of-00004.safetensors",
+        "model.layers.0.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.1.mlp.down_proj.biases": "model-00001-of-00004.safetensors",
+        "model.layers.1.mlp.down_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.1.mlp.gate_proj.biases": "model-00001-of-00004.safetensors",
+        "model.layers.1.mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.1.mlp.up_proj.biases": "model-00001-of-00004.safetensors",
+        "model.layers.1.mlp.up_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.1.self_attn.k_proj.biases": "model-00001-of-00004.safetensors",
+        "model.layers.1.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.1.self_attn.o_proj.biases": "model-00001-of-00004.safetensors",
+        "model.layers.1.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.1.self_attn.q_proj.biases": "model-00001-of-00004.safetensors",
+        "model.layers.1.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.1.self_attn.v_proj.biases": "model-00001-of-00004.safetensors",
+        "model.layers.1.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.10.input_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.10.mlp.down_proj.biases": "model-00001-of-00004.safetensors",
+        "model.layers.10.mlp.down_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.10.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.10.mlp.gate_proj.biases": "model-00001-of-00004.safetensors",
+        "model.layers.10.mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.10.mlp.up_proj.biases": "model-00001-of-00004.safetensors",
+        "model.layers.10.mlp.up_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.10.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.10.self_attn.k_proj.biases": "model-00001-of-00004.safetensors",
+        "model.layers.10.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.10.self_attn.o_proj.biases": "model-00001-of-00004.safetensors",
+        "model.layers.10.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.10.self_attn.q_proj.biases": "model-00001-of-00004.safetensors",
+        "model.layers.10.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.10.self_attn.v_proj.biases": "model-00001-of-00004.safetensors",
+        "model.layers.10.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.11.input_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.11.mlp.down_proj.biases": "model-00001-of-00004.safetensors",
+        "model.layers.11.mlp.down_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.11.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.11.mlp.gate_proj.biases": "model-00001-of-00004.safetensors",
+        "model.layers.11.mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.11.mlp.up_proj.biases": "model-00001-of-00004.safetensors",
+        "model.layers.11.mlp.up_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.11.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.11.self_attn.k_proj.biases": "model-00001-of-00004.safetensors",
+        "model.layers.11.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.11.self_attn.o_proj.biases": "model-00001-of-00004.safetensors",
+        "model.layers.11.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.11.self_attn.q_proj.biases": "model-00001-of-00004.safetensors",
+        "model.layers.11.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.11.self_attn.v_proj.biases": "model-00001-of-00004.safetensors",
+        "model.layers.11.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.12.input_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.12.mlp.down_proj.biases": "model-00001-of-00004.safetensors",
+        "model.layers.12.mlp.down_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.12.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.12.mlp.gate_proj.biases": "model-00001-of-00004.safetensors",
+        "model.layers.12.mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.12.mlp.up_proj.biases": "model-00001-of-00004.safetensors",
+        "model.layers.12.mlp.up_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.12.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.12.self_attn.k_proj.biases": "model-00001-of-00004.safetensors",
+        "model.layers.12.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.12.self_attn.o_proj.biases": "model-00001-of-00004.safetensors",
+        "model.layers.12.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.12.self_attn.q_proj.biases": "model-00001-of-00004.safetensors",
+        "model.layers.12.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.12.self_attn.v_proj.biases": "model-00001-of-00004.safetensors",
+        "model.layers.12.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.13.mlp.down_proj.biases": "model-00002-of-00004.safetensors",
+        "model.layers.13.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.13.mlp.gate_proj.biases": "model-00002-of-00004.safetensors",
+        "model.layers.13.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.13.mlp.up_proj.biases": "model-00002-of-00004.safetensors",
+        "model.layers.13.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.13.self_attn.k_proj.biases": "model-00001-of-00004.safetensors",
+        "model.layers.13.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.13.self_attn.o_proj.biases": "model-00001-of-00004.safetensors",
+        "model.layers.13.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.13.self_attn.q_proj.biases": "model-00001-of-00004.safetensors",
+        "model.layers.13.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.13.self_attn.v_proj.biases": "model-00001-of-00004.safetensors",
+        "model.layers.13.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.14.mlp.down_proj.biases": "model-00002-of-00004.safetensors",
+        "model.layers.14.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.14.mlp.gate_proj.biases": "model-00002-of-00004.safetensors",
+        "model.layers.14.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.14.mlp.up_proj.biases": "model-00002-of-00004.safetensors",
+        "model.layers.14.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.14.self_attn.k_proj.biases": "model-00002-of-00004.safetensors",
+        "model.layers.14.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.14.self_attn.o_proj.biases": "model-00002-of-00004.safetensors",
+        "model.layers.14.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.14.self_attn.q_proj.biases": "model-00002-of-00004.safetensors",
+        "model.layers.14.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.14.self_attn.v_proj.biases": "model-00002-of-00004.safetensors",
+        "model.layers.14.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.15.mlp.down_proj.biases": "model-00002-of-00004.safetensors",
+        "model.layers.15.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.15.mlp.gate_proj.biases": "model-00002-of-00004.safetensors",
+        "model.layers.15.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.15.mlp.up_proj.biases": "model-00002-of-00004.safetensors",
+        "model.layers.15.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.15.self_attn.k_proj.biases": "model-00002-of-00004.safetensors",
+        "model.layers.15.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.15.self_attn.o_proj.biases": "model-00002-of-00004.safetensors",
+        "model.layers.15.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.15.self_attn.q_proj.biases": "model-00002-of-00004.safetensors",
+        "model.layers.15.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.15.self_attn.v_proj.biases": "model-00002-of-00004.safetensors",
+        "model.layers.15.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.16.mlp.down_proj.biases": "model-00002-of-00004.safetensors",
+        "model.layers.16.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.16.mlp.gate_proj.biases": "model-00002-of-00004.safetensors",
+        "model.layers.16.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.16.mlp.up_proj.biases": "model-00002-of-00004.safetensors",
+        "model.layers.16.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.16.self_attn.k_proj.biases": "model-00002-of-00004.safetensors",
+        "model.layers.16.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.16.self_attn.o_proj.biases": "model-00002-of-00004.safetensors",
+        "model.layers.16.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.16.self_attn.q_proj.biases": "model-00002-of-00004.safetensors",
+        "model.layers.16.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.16.self_attn.v_proj.biases": "model-00002-of-00004.safetensors",
+        "model.layers.16.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.17.mlp.down_proj.biases": "model-00002-of-00004.safetensors",
+        "model.layers.17.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.17.mlp.gate_proj.biases": "model-00002-of-00004.safetensors",
+        "model.layers.17.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.17.mlp.up_proj.biases": "model-00002-of-00004.safetensors",
+        "model.layers.17.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.17.self_attn.k_proj.biases": "model-00002-of-00004.safetensors",
+        "model.layers.17.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.17.self_attn.o_proj.biases": "model-00002-of-00004.safetensors",
+        "model.layers.17.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.17.self_attn.q_proj.biases": "model-00002-of-00004.safetensors",
+        "model.layers.17.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.17.self_attn.v_proj.biases": "model-00002-of-00004.safetensors",
+        "model.layers.17.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.18.mlp.down_proj.biases": "model-00002-of-00004.safetensors",
+        "model.layers.18.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.18.mlp.gate_proj.biases": "model-00002-of-00004.safetensors",
+        "model.layers.18.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.18.mlp.up_proj.biases": "model-00002-of-00004.safetensors",
+        "model.layers.18.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.18.self_attn.k_proj.biases": "model-00002-of-00004.safetensors",
+        "model.layers.18.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.18.self_attn.o_proj.biases": "model-00002-of-00004.safetensors",
+        "model.layers.18.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.18.self_attn.q_proj.biases": "model-00002-of-00004.safetensors",
+        "model.layers.18.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.18.self_attn.v_proj.biases": "model-00002-of-00004.safetensors",
+        "model.layers.18.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.19.mlp.down_proj.biases": "model-00002-of-00004.safetensors",
+        "model.layers.19.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.19.mlp.gate_proj.biases": "model-00002-of-00004.safetensors",
+        "model.layers.19.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.19.mlp.up_proj.biases": "model-00002-of-00004.safetensors",
+        "model.layers.19.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.19.self_attn.k_proj.biases": "model-00002-of-00004.safetensors",
+        "model.layers.19.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.19.self_attn.o_proj.biases": "model-00002-of-00004.safetensors",
+        "model.layers.19.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.19.self_attn.q_proj.biases": "model-00002-of-00004.safetensors",
+        "model.layers.19.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.19.self_attn.v_proj.biases": "model-00002-of-00004.safetensors",
+        "model.layers.19.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.2.mlp.down_proj.biases": "model-00001-of-00004.safetensors",
+        "model.layers.2.mlp.down_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.2.mlp.gate_proj.biases": "model-00001-of-00004.safetensors",
+        "model.layers.2.mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.2.mlp.up_proj.biases": "model-00001-of-00004.safetensors",
+        "model.layers.2.mlp.up_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.2.self_attn.k_proj.biases": "model-00001-of-00004.safetensors",
+        "model.layers.2.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.2.self_attn.o_proj.biases": "model-00001-of-00004.safetensors",
+        "model.layers.2.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.2.self_attn.q_proj.biases": "model-00001-of-00004.safetensors",
+        "model.layers.2.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.2.self_attn.v_proj.biases": "model-00001-of-00004.safetensors",
+        "model.layers.2.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.20.mlp.down_proj.biases": "model-00002-of-00004.safetensors",
+        "model.layers.20.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.20.mlp.gate_proj.biases": "model-00002-of-00004.safetensors",
+        "model.layers.20.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.20.mlp.up_proj.biases": "model-00002-of-00004.safetensors",
+        "model.layers.20.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.20.self_attn.k_proj.biases": "model-00002-of-00004.safetensors",
+        "model.layers.20.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.20.self_attn.o_proj.biases": "model-00002-of-00004.safetensors",
+        "model.layers.20.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.20.self_attn.q_proj.biases": "model-00002-of-00004.safetensors",
+        "model.layers.20.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.20.self_attn.v_proj.biases": "model-00002-of-00004.safetensors",
+        "model.layers.20.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.21.mlp.down_proj.biases": "model-00002-of-00004.safetensors",
+        "model.layers.21.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.21.mlp.gate_proj.biases": "model-00002-of-00004.safetensors",
+        "model.layers.21.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.21.mlp.up_proj.biases": "model-00002-of-00004.safetensors",
+        "model.layers.21.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.21.self_attn.k_proj.biases": "model-00002-of-00004.safetensors",
+        "model.layers.21.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.21.self_attn.o_proj.biases": "model-00002-of-00004.safetensors",
+        "model.layers.21.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.21.self_attn.q_proj.biases": "model-00002-of-00004.safetensors",
+        "model.layers.21.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.21.self_attn.v_proj.biases": "model-00002-of-00004.safetensors",
+        "model.layers.21.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.22.input_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.22.mlp.down_proj.biases": "model-00002-of-00004.safetensors",
+        "model.layers.22.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.22.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.22.mlp.gate_proj.biases": "model-00002-of-00004.safetensors",
+        "model.layers.22.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.22.mlp.up_proj.biases": "model-00002-of-00004.safetensors",
+        "model.layers.22.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.22.self_attn.k_proj.biases": "model-00002-of-00004.safetensors",
+        "model.layers.22.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.22.self_attn.o_proj.biases": "model-00002-of-00004.safetensors",
+        "model.layers.22.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.22.self_attn.q_proj.biases": "model-00002-of-00004.safetensors",
+        "model.layers.22.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.22.self_attn.v_proj.biases": "model-00002-of-00004.safetensors",
+        "model.layers.22.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.23.input_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.23.mlp.down_proj.biases": "model-00002-of-00004.safetensors",
+        "model.layers.23.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.23.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.23.mlp.gate_proj.biases": "model-00002-of-00004.safetensors",
+        "model.layers.23.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.23.mlp.up_proj.biases": "model-00002-of-00004.safetensors",
+        "model.layers.23.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.23.self_attn.k_proj.biases": "model-00002-of-00004.safetensors",
+        "model.layers.23.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.23.self_attn.o_proj.biases": "model-00002-of-00004.safetensors",
+        "model.layers.23.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.23.self_attn.q_proj.biases": "model-00002-of-00004.safetensors",
+        "model.layers.23.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.23.self_attn.v_proj.biases": "model-00002-of-00004.safetensors",
+        "model.layers.23.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.24.input_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.24.mlp.down_proj.biases": "model-00002-of-00004.safetensors",
+        "model.layers.24.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.24.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.24.mlp.gate_proj.biases": "model-00002-of-00004.safetensors",
+        "model.layers.24.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.24.mlp.up_proj.biases": "model-00002-of-00004.safetensors",
+        "model.layers.24.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.24.self_attn.k_proj.biases": "model-00002-of-00004.safetensors",
+        "model.layers.24.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.24.self_attn.o_proj.biases": "model-00002-of-00004.safetensors",
+        "model.layers.24.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.24.self_attn.q_proj.biases": "model-00002-of-00004.safetensors",
+        "model.layers.24.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.24.self_attn.v_proj.biases": "model-00002-of-00004.safetensors",
+        "model.layers.24.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.25.input_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.25.mlp.down_proj.biases": "model-00002-of-00004.safetensors",
+        "model.layers.25.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.25.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.25.mlp.gate_proj.biases": "model-00002-of-00004.safetensors",
+        "model.layers.25.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.25.mlp.up_proj.biases": "model-00002-of-00004.safetensors",
+        "model.layers.25.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.25.self_attn.k_proj.biases": "model-00002-of-00004.safetensors",
+        "model.layers.25.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.25.self_attn.o_proj.biases": "model-00002-of-00004.safetensors",
+        "model.layers.25.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.25.self_attn.q_proj.biases": "model-00002-of-00004.safetensors",
+        "model.layers.25.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.25.self_attn.v_proj.biases": "model-00002-of-00004.safetensors",
+        "model.layers.25.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.26.input_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.26.mlp.down_proj.biases": "model-00002-of-00004.safetensors",
+        "model.layers.26.mlp.down_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.26.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.26.mlp.gate_proj.biases": "model-00002-of-00004.safetensors",
+        "model.layers.26.mlp.gate_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.26.mlp.up_proj.biases": "model-00002-of-00004.safetensors",
+        "model.layers.26.mlp.up_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.26.self_attn.k_proj.biases": "model-00002-of-00004.safetensors",
+        "model.layers.26.self_attn.k_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.26.self_attn.o_proj.biases": "model-00002-of-00004.safetensors",
+        "model.layers.26.self_attn.o_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.26.self_attn.q_proj.biases": "model-00002-of-00004.safetensors",
+        "model.layers.26.self_attn.q_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.26.self_attn.v_proj.biases": "model-00002-of-00004.safetensors",
+        "model.layers.26.self_attn.v_proj.scales": "model-00002-of-00004.safetensors",
+        "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.27.mlp.down_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.27.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.27.mlp.gate_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.27.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.27.mlp.up_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.27.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.27.self_attn.k_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.27.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.27.self_attn.o_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.27.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.27.self_attn.q_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.27.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.27.self_attn.v_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.27.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.28.mlp.down_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.28.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.28.mlp.gate_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.28.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.28.mlp.up_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.28.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.28.self_attn.k_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.28.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.28.self_attn.o_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.28.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.28.self_attn.q_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.28.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.28.self_attn.v_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.28.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.29.mlp.down_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.29.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.29.mlp.gate_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.29.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.29.mlp.up_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.29.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.29.self_attn.k_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.29.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.29.self_attn.o_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.29.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.29.self_attn.q_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.29.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.29.self_attn.v_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.29.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.3.mlp.down_proj.biases": "model-00001-of-00004.safetensors",
+        "model.layers.3.mlp.down_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.3.mlp.gate_proj.biases": "model-00001-of-00004.safetensors",
+        "model.layers.3.mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.3.mlp.up_proj.biases": "model-00001-of-00004.safetensors",
+        "model.layers.3.mlp.up_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.3.self_attn.k_proj.biases": "model-00001-of-00004.safetensors",
+        "model.layers.3.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.3.self_attn.o_proj.biases": "model-00001-of-00004.safetensors",
+        "model.layers.3.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.3.self_attn.q_proj.biases": "model-00001-of-00004.safetensors",
+        "model.layers.3.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.3.self_attn.v_proj.biases": "model-00001-of-00004.safetensors",
+        "model.layers.3.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.30.mlp.down_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.30.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.30.mlp.gate_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.30.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.30.mlp.up_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.30.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.30.self_attn.k_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.30.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.30.self_attn.o_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.30.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.30.self_attn.q_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.30.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.30.self_attn.v_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.30.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.31.mlp.down_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.31.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.31.mlp.gate_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.31.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.31.mlp.up_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.31.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.31.self_attn.k_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.31.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.31.self_attn.o_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.31.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.31.self_attn.q_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.31.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.31.self_attn.v_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.31.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.32.mlp.down_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.32.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.32.mlp.gate_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.32.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.32.mlp.up_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.32.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.32.self_attn.k_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.32.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.32.self_attn.o_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.32.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.32.self_attn.q_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.32.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.32.self_attn.v_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.32.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.33.mlp.down_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.33.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.33.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.33.mlp.gate_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.33.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.33.mlp.up_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.33.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.33.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.33.self_attn.k_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.33.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.33.self_attn.o_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.33.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.33.self_attn.q_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.33.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.33.self_attn.v_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.33.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.34.mlp.down_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.34.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.34.mlp.gate_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.34.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.34.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.34.mlp.up_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.34.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.34.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.34.self_attn.k_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.34.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.34.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.34.self_attn.o_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.34.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.34.self_attn.q_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.34.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.34.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.34.self_attn.v_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.34.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.35.input_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.35.mlp.down_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.35.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.35.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.35.mlp.gate_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.35.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.35.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.35.mlp.up_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.35.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.35.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.35.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.35.self_attn.k_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.35.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.35.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.35.self_attn.o_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.35.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.35.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.35.self_attn.q_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.35.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.35.self_attn.v_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.35.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.35.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.36.input_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.36.mlp.down_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.36.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.36.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.36.mlp.gate_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.36.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.36.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.36.mlp.up_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.36.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.36.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.36.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.36.self_attn.k_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.36.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.36.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.36.self_attn.o_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.36.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.36.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.36.self_attn.q_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.36.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.36.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.36.self_attn.v_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.36.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.36.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.37.input_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.37.mlp.down_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.37.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.37.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.37.mlp.gate_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.37.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.37.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.37.mlp.up_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.37.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.37.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.37.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.37.self_attn.k_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.37.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.37.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.37.self_attn.o_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.37.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.37.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.37.self_attn.q_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.37.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.37.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.37.self_attn.v_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.37.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.37.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.38.input_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.38.mlp.down_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.38.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.38.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.38.mlp.gate_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.38.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.38.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.38.mlp.up_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.38.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.38.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.38.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.38.self_attn.k_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.38.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.38.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.38.self_attn.o_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.38.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.38.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.38.self_attn.q_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.38.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.38.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.38.self_attn.v_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.38.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.38.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.39.input_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.39.mlp.down_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.39.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.39.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.39.mlp.gate_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.39.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.39.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.39.mlp.up_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.39.mlp.up_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.39.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.39.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.39.self_attn.k_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.39.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.39.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.39.self_attn.o_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.39.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.39.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.39.self_attn.q_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.39.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.39.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.39.self_attn.v_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.39.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.39.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.4.mlp.down_proj.biases": "model-00001-of-00004.safetensors",
+        "model.layers.4.mlp.down_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.4.mlp.gate_proj.biases": "model-00001-of-00004.safetensors",
+        "model.layers.4.mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.4.mlp.up_proj.biases": "model-00001-of-00004.safetensors",
+        "model.layers.4.mlp.up_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.4.self_attn.k_proj.biases": "model-00001-of-00004.safetensors",
+        "model.layers.4.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.4.self_attn.o_proj.biases": "model-00001-of-00004.safetensors",
+        "model.layers.4.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.4.self_attn.q_proj.biases": "model-00001-of-00004.safetensors",
+        "model.layers.4.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.4.self_attn.v_proj.biases": "model-00001-of-00004.safetensors",
+        "model.layers.4.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.40.input_layernorm.weight": "model-00004-of-00004.safetensors",
+        "model.layers.40.mlp.down_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.40.mlp.down_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.40.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.40.mlp.gate_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.40.mlp.gate_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.40.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.40.mlp.up_proj.biases": "model-00004-of-00004.safetensors",
+        "model.layers.40.mlp.up_proj.scales": "model-00004-of-00004.safetensors",
+        "model.layers.40.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+        "model.layers.40.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+        "model.layers.40.self_attn.k_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.40.self_attn.k_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.40.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.40.self_attn.o_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.40.self_attn.o_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.40.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.40.self_attn.q_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.40.self_attn.q_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.40.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.40.self_attn.v_proj.biases": "model-00003-of-00004.safetensors",
+        "model.layers.40.self_attn.v_proj.scales": "model-00003-of-00004.safetensors",
+        "model.layers.40.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.41.input_layernorm.weight": "model-00004-of-00004.safetensors",
+        "model.layers.41.mlp.down_proj.biases": "model-00004-of-00004.safetensors",
+        "model.layers.41.mlp.down_proj.scales": "model-00004-of-00004.safetensors",
+        "model.layers.41.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+        "model.layers.41.mlp.gate_proj.biases": "model-00004-of-00004.safetensors",
+        "model.layers.41.mlp.gate_proj.scales": "model-00004-of-00004.safetensors",
+        "model.layers.41.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+        "model.layers.41.mlp.up_proj.biases": "model-00004-of-00004.safetensors",
+        "model.layers.41.mlp.up_proj.scales": "model-00004-of-00004.safetensors",
+        "model.layers.41.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+        "model.layers.41.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+        "model.layers.41.self_attn.k_proj.biases": "model-00004-of-00004.safetensors",
+        "model.layers.41.self_attn.k_proj.scales": "model-00004-of-00004.safetensors",
+        "model.layers.41.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+        "model.layers.41.self_attn.o_proj.biases": "model-00004-of-00004.safetensors",
+        "model.layers.41.self_attn.o_proj.scales": "model-00004-of-00004.safetensors",
+        "model.layers.41.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+        "model.layers.41.self_attn.q_proj.biases": "model-00004-of-00004.safetensors",
+        "model.layers.41.self_attn.q_proj.scales": "model-00004-of-00004.safetensors",
+        "model.layers.41.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+        "model.layers.41.self_attn.v_proj.biases": "model-00004-of-00004.safetensors",
+        "model.layers.41.self_attn.v_proj.scales": "model-00004-of-00004.safetensors",
+        "model.layers.41.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+        "model.layers.42.input_layernorm.weight": "model-00004-of-00004.safetensors",
+        "model.layers.42.mlp.down_proj.biases": "model-00004-of-00004.safetensors",
+        "model.layers.42.mlp.down_proj.scales": "model-00004-of-00004.safetensors",
+        "model.layers.42.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+        "model.layers.42.mlp.gate_proj.biases": "model-00004-of-00004.safetensors",
+        "model.layers.42.mlp.gate_proj.scales": "model-00004-of-00004.safetensors",
+        "model.layers.42.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+        "model.layers.42.mlp.up_proj.biases": "model-00004-of-00004.safetensors",
+        "model.layers.42.mlp.up_proj.scales": "model-00004-of-00004.safetensors",
+        "model.layers.42.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+        "model.layers.42.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+        "model.layers.42.self_attn.k_proj.biases": "model-00004-of-00004.safetensors",
+        "model.layers.42.self_attn.k_proj.scales": "model-00004-of-00004.safetensors",
+        "model.layers.42.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+        "model.layers.42.self_attn.o_proj.biases": "model-00004-of-00004.safetensors",
+        "model.layers.42.self_attn.o_proj.scales": "model-00004-of-00004.safetensors",
+        "model.layers.42.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+        "model.layers.42.self_attn.q_proj.biases": "model-00004-of-00004.safetensors",
+        "model.layers.42.self_attn.q_proj.scales": "model-00004-of-00004.safetensors",
+        "model.layers.42.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+        "model.layers.42.self_attn.v_proj.biases": "model-00004-of-00004.safetensors",
+        "model.layers.42.self_attn.v_proj.scales": "model-00004-of-00004.safetensors",
+        "model.layers.42.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+        "model.layers.43.input_layernorm.weight": "model-00004-of-00004.safetensors",
+        "model.layers.43.mlp.down_proj.biases": "model-00004-of-00004.safetensors",
+        "model.layers.43.mlp.down_proj.scales": "model-00004-of-00004.safetensors",
+        "model.layers.43.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+        "model.layers.43.mlp.gate_proj.biases": "model-00004-of-00004.safetensors",
+        "model.layers.43.mlp.gate_proj.scales": "model-00004-of-00004.safetensors",
+        "model.layers.43.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+        "model.layers.43.mlp.up_proj.biases": "model-00004-of-00004.safetensors",
+        "model.layers.43.mlp.up_proj.scales": "model-00004-of-00004.safetensors",
+        "model.layers.43.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+        "model.layers.43.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+        "model.layers.43.self_attn.k_proj.biases": "model-00004-of-00004.safetensors",
+        "model.layers.43.self_attn.k_proj.scales": "model-00004-of-00004.safetensors",
+        "model.layers.43.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+        "model.layers.43.self_attn.o_proj.biases": "model-00004-of-00004.safetensors",
+        "model.layers.43.self_attn.o_proj.scales": "model-00004-of-00004.safetensors",
+        "model.layers.43.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+        "model.layers.43.self_attn.q_proj.biases": "model-00004-of-00004.safetensors",
+        "model.layers.43.self_attn.q_proj.scales": "model-00004-of-00004.safetensors",
+        "model.layers.43.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+        "model.layers.43.self_attn.v_proj.biases": "model-00004-of-00004.safetensors",
+        "model.layers.43.self_attn.v_proj.scales": "model-00004-of-00004.safetensors",
+        "model.layers.43.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+        "model.layers.44.input_layernorm.weight": "model-00004-of-00004.safetensors",
+        "model.layers.44.mlp.down_proj.biases": "model-00004-of-00004.safetensors",
+        "model.layers.44.mlp.down_proj.scales": "model-00004-of-00004.safetensors",
+        "model.layers.44.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+        "model.layers.44.mlp.gate_proj.biases": "model-00004-of-00004.safetensors",
+        "model.layers.44.mlp.gate_proj.scales": "model-00004-of-00004.safetensors",
+        "model.layers.44.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+        "model.layers.44.mlp.up_proj.biases": "model-00004-of-00004.safetensors",
+        "model.layers.44.mlp.up_proj.scales": "model-00004-of-00004.safetensors",
+        "model.layers.44.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+        "model.layers.44.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+        "model.layers.44.self_attn.k_proj.biases": "model-00004-of-00004.safetensors",
+        "model.layers.44.self_attn.k_proj.scales": "model-00004-of-00004.safetensors",
+        "model.layers.44.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+        "model.layers.44.self_attn.o_proj.biases": "model-00004-of-00004.safetensors",
+        "model.layers.44.self_attn.o_proj.scales": "model-00004-of-00004.safetensors",
+        "model.layers.44.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+        "model.layers.44.self_attn.q_proj.biases": "model-00004-of-00004.safetensors",
+        "model.layers.44.self_attn.q_proj.scales": "model-00004-of-00004.safetensors",
+        "model.layers.44.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+        "model.layers.44.self_attn.v_proj.biases": "model-00004-of-00004.safetensors",
+        "model.layers.44.self_attn.v_proj.scales": "model-00004-of-00004.safetensors",
+        "model.layers.44.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+        "model.layers.45.input_layernorm.weight": "model-00004-of-00004.safetensors",
+        "model.layers.45.mlp.down_proj.biases": "model-00004-of-00004.safetensors",
+        "model.layers.45.mlp.down_proj.scales": "model-00004-of-00004.safetensors",
+        "model.layers.45.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+        "model.layers.45.mlp.gate_proj.biases": "model-00004-of-00004.safetensors",
+        "model.layers.45.mlp.gate_proj.scales": "model-00004-of-00004.safetensors",
+        "model.layers.45.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+        "model.layers.45.mlp.up_proj.biases": "model-00004-of-00004.safetensors",
+        "model.layers.45.mlp.up_proj.scales": "model-00004-of-00004.safetensors",
+        "model.layers.45.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+        "model.layers.45.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+        "model.layers.45.self_attn.k_proj.biases": "model-00004-of-00004.safetensors",
+        "model.layers.45.self_attn.k_proj.scales": "model-00004-of-00004.safetensors",
+        "model.layers.45.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+        "model.layers.45.self_attn.o_proj.biases": "model-00004-of-00004.safetensors",
+        "model.layers.45.self_attn.o_proj.scales": "model-00004-of-00004.safetensors",
+        "model.layers.45.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+        "model.layers.45.self_attn.q_proj.biases": "model-00004-of-00004.safetensors",
+        "model.layers.45.self_attn.q_proj.scales": "model-00004-of-00004.safetensors",
+        "model.layers.45.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+        "model.layers.45.self_attn.v_proj.biases": "model-00004-of-00004.safetensors",
+        "model.layers.45.self_attn.v_proj.scales": "model-00004-of-00004.safetensors",
+        "model.layers.45.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+        "model.layers.46.input_layernorm.weight": "model-00004-of-00004.safetensors",
+        "model.layers.46.mlp.down_proj.biases": "model-00004-of-00004.safetensors",
+        "model.layers.46.mlp.down_proj.scales": "model-00004-of-00004.safetensors",
+        "model.layers.46.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+        "model.layers.46.mlp.gate_proj.biases": "model-00004-of-00004.safetensors",
+        "model.layers.46.mlp.gate_proj.scales": "model-00004-of-00004.safetensors",
+        "model.layers.46.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+        "model.layers.46.mlp.up_proj.biases": "model-00004-of-00004.safetensors",
+        "model.layers.46.mlp.up_proj.scales": "model-00004-of-00004.safetensors",
+        "model.layers.46.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+        "model.layers.46.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+        "model.layers.46.self_attn.k_proj.biases": "model-00004-of-00004.safetensors",
+        "model.layers.46.self_attn.k_proj.scales": "model-00004-of-00004.safetensors",
+        "model.layers.46.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+        "model.layers.46.self_attn.o_proj.biases": "model-00004-of-00004.safetensors",
+        "model.layers.46.self_attn.o_proj.scales": "model-00004-of-00004.safetensors",
+        "model.layers.46.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+        "model.layers.46.self_attn.q_proj.biases": "model-00004-of-00004.safetensors",
+        "model.layers.46.self_attn.q_proj.scales": "model-00004-of-00004.safetensors",
+        "model.layers.46.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+        "model.layers.46.self_attn.v_proj.biases": "model-00004-of-00004.safetensors",
+        "model.layers.46.self_attn.v_proj.scales": "model-00004-of-00004.safetensors",
+        "model.layers.46.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+        "model.layers.47.input_layernorm.weight": "model-00004-of-00004.safetensors",
+        "model.layers.47.mlp.down_proj.biases": "model-00004-of-00004.safetensors",
+        "model.layers.47.mlp.down_proj.scales": "model-00004-of-00004.safetensors",
+        "model.layers.47.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+        "model.layers.47.mlp.gate_proj.biases": "model-00004-of-00004.safetensors",
+        "model.layers.47.mlp.gate_proj.scales": "model-00004-of-00004.safetensors",
+        "model.layers.47.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+        "model.layers.47.mlp.up_proj.biases": "model-00004-of-00004.safetensors",
+        "model.layers.47.mlp.up_proj.scales": "model-00004-of-00004.safetensors",
+        "model.layers.47.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+        "model.layers.47.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+        "model.layers.47.self_attn.k_proj.biases": "model-00004-of-00004.safetensors",
+        "model.layers.47.self_attn.k_proj.scales": "model-00004-of-00004.safetensors",
+        "model.layers.47.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+        "model.layers.47.self_attn.o_proj.biases": "model-00004-of-00004.safetensors",
+        "model.layers.47.self_attn.o_proj.scales": "model-00004-of-00004.safetensors",
+        "model.layers.47.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+        "model.layers.47.self_attn.q_proj.biases": "model-00004-of-00004.safetensors",
+        "model.layers.47.self_attn.q_proj.scales": "model-00004-of-00004.safetensors",
+        "model.layers.47.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+        "model.layers.47.self_attn.v_proj.biases": "model-00004-of-00004.safetensors",
+        "model.layers.47.self_attn.v_proj.scales": "model-00004-of-00004.safetensors",
+        "model.layers.47.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+        "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.5.mlp.down_proj.biases": "model-00001-of-00004.safetensors",
+        "model.layers.5.mlp.down_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.5.mlp.gate_proj.biases": "model-00001-of-00004.safetensors",
+        "model.layers.5.mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.5.mlp.up_proj.biases": "model-00001-of-00004.safetensors",
+        "model.layers.5.mlp.up_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.5.self_attn.k_proj.biases": "model-00001-of-00004.safetensors",
+        "model.layers.5.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.5.self_attn.o_proj.biases": "model-00001-of-00004.safetensors",
+        "model.layers.5.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.5.self_attn.q_proj.biases": "model-00001-of-00004.safetensors",
+        "model.layers.5.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.5.self_attn.v_proj.biases": "model-00001-of-00004.safetensors",
+        "model.layers.5.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.6.mlp.down_proj.biases": "model-00001-of-00004.safetensors",
+        "model.layers.6.mlp.down_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.6.mlp.gate_proj.biases": "model-00001-of-00004.safetensors",
+        "model.layers.6.mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.6.mlp.up_proj.biases": "model-00001-of-00004.safetensors",
+        "model.layers.6.mlp.up_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.6.self_attn.k_proj.biases": "model-00001-of-00004.safetensors",
+        "model.layers.6.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.6.self_attn.o_proj.biases": "model-00001-of-00004.safetensors",
+        "model.layers.6.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.6.self_attn.q_proj.biases": "model-00001-of-00004.safetensors",
+        "model.layers.6.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.6.self_attn.v_proj.biases": "model-00001-of-00004.safetensors",
+        "model.layers.6.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.7.mlp.down_proj.biases": "model-00001-of-00004.safetensors",
+        "model.layers.7.mlp.down_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.7.mlp.gate_proj.biases": "model-00001-of-00004.safetensors",
+        "model.layers.7.mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.7.mlp.up_proj.biases": "model-00001-of-00004.safetensors",
+        "model.layers.7.mlp.up_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.7.self_attn.k_proj.biases": "model-00001-of-00004.safetensors",
+        "model.layers.7.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.7.self_attn.o_proj.biases": "model-00001-of-00004.safetensors",
+        "model.layers.7.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.7.self_attn.q_proj.biases": "model-00001-of-00004.safetensors",
+        "model.layers.7.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.7.self_attn.v_proj.biases": "model-00001-of-00004.safetensors",
+        "model.layers.7.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.8.mlp.down_proj.biases": "model-00001-of-00004.safetensors",
+        "model.layers.8.mlp.down_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.8.mlp.gate_proj.biases": "model-00001-of-00004.safetensors",
+        "model.layers.8.mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.8.mlp.up_proj.biases": "model-00001-of-00004.safetensors",
+        "model.layers.8.mlp.up_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.8.self_attn.k_proj.biases": "model-00001-of-00004.safetensors",
+        "model.layers.8.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.8.self_attn.o_proj.biases": "model-00001-of-00004.safetensors",
+        "model.layers.8.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.8.self_attn.q_proj.biases": "model-00001-of-00004.safetensors",
+        "model.layers.8.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.8.self_attn.v_proj.biases": "model-00001-of-00004.safetensors",
+        "model.layers.8.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.9.input_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.9.mlp.down_proj.biases": "model-00001-of-00004.safetensors",
+        "model.layers.9.mlp.down_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.9.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.9.mlp.gate_proj.biases": "model-00001-of-00004.safetensors",
+        "model.layers.9.mlp.gate_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.9.mlp.up_proj.biases": "model-00001-of-00004.safetensors",
+        "model.layers.9.mlp.up_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.9.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.9.self_attn.k_proj.biases": "model-00001-of-00004.safetensors",
+        "model.layers.9.self_attn.k_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.9.self_attn.o_proj.biases": "model-00001-of-00004.safetensors",
+        "model.layers.9.self_attn.o_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.9.self_attn.q_proj.biases": "model-00001-of-00004.safetensors",
+        "model.layers.9.self_attn.q_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.9.self_attn.v_proj.biases": "model-00001-of-00004.safetensors",
+        "model.layers.9.self_attn.v_proj.scales": "model-00001-of-00004.safetensors",
+        "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+        "model.norm.weight": "model-00004-of-00004.safetensors"
+    }
+}

special_tokens_map.json

@@ -0,0 +1,29 @@
+{
+  "additional_special_tokens": [
+    "▁<PRE>",
+    "▁<MID>",
+    "▁<SUF>",
+    "▁<EOT>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,84 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "▁<PRE>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "▁<MID>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "▁<SUF>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32003": {
+      "content": "▁<EOT>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "▁<PRE>",
+    "▁<MID>",
+    "▁<SUF>",
+    "▁<EOT>"
+  ],
+  "bos_token": "<s>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + content | trim + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' '  + content | trim + ' ' + eos_token }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "eot_token": "▁<EOT>",
+  "fill_token": "<FILL_ME>",
+  "legacy": null,
+  "middle_token": "▁<MID>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "prefix_token": "▁<PRE>",
+  "sp_model_kwargs": {},
+  "suffix_token": "▁<SUF>",
+  "tokenizer_class": "CodeLlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

zero_to_fp32.py

@@ -0,0 +1,578 @@
+#!/usr/bin/env python
+
+# Copyright (c) Microsoft Corporation.
+# SPDX-License-Identifier: Apache-2.0
+
+# DeepSpeed Team
+
+# This script extracts fp32 consolidated weights from a zero 2 and 3 DeepSpeed checkpoints. It gets
+# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
+# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
+# application.
+#
+# example: python zero_to_fp32.py . pytorch_model.bin
+
+import argparse
+import torch
+import glob
+import math
+import os
+import re
+from collections import OrderedDict
+from dataclasses import dataclass
+
+# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
+# DeepSpeed data structures it has to be available in the current python environment.
+from deepspeed.utils import logger
+from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
+                                            FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
+                                            FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
+
+
+@dataclass
+class zero_model_state:
+    buffers: dict()
+    param_shapes: dict()
+    shared_params: list
+    ds_version: int
+    frozen_param_shapes: dict()
+    frozen_param_fragments: dict()
+
+
+debug = 0
+
+# load to cpu
+device = torch.device('cpu')
+
+
+def atoi(text):
+    return int(text) if text.isdigit() else text
+
+
+def natural_keys(text):
+    '''
+    alist.sort(key=natural_keys) sorts in human order
+    http://nedbatchelder.com/blog/200712/human_sorting.html
+    (See Toothy's implementation in the comments)
+    '''
+    return [atoi(c) for c in re.split(r'(\d+)', text)]
+
+
+def get_model_state_file(checkpoint_dir, zero_stage):
+    if not os.path.isdir(checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
+
+    # there should be only one file
+    if zero_stage == 2:
+        file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
+    elif zero_stage == 3:
+        file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
+
+    if not os.path.exists(file):
+        raise FileNotFoundError(f"can't find model states file at '{file}'")
+
+    return file
+
+
+def get_checkpoint_files(checkpoint_dir, glob_pattern):
+    # XXX: need to test that this simple glob rule works for multi-node setup too
+    ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
+
+    if len(ckpt_files) == 0:
+        raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
+
+    return ckpt_files
+
+
+def get_optim_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
+
+
+def get_model_state_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
+
+
+def parse_model_states(files):
+    zero_model_states = []
+    for file in files:
+        state_dict = torch.load(file, map_location=device)
+
+        if BUFFER_NAMES not in state_dict:
+            raise ValueError(f"{file} is not a model state checkpoint")
+        buffer_names = state_dict[BUFFER_NAMES]
+        if debug:
+            print("Found buffers:", buffer_names)
+
+        # recover just the buffers while restoring them to fp32 if they were saved in fp16
+        buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
+        param_shapes = state_dict[PARAM_SHAPES]
+
+        # collect parameters that are included in param_shapes
+        param_names = []
+        for s in param_shapes:
+            for name in s.keys():
+                param_names.append(name)
+
+        # update with frozen parameters
+        frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
+        if frozen_param_shapes is not None:
+            if debug:
+                print(f"Found frozen_param_shapes: {frozen_param_shapes}")
+            param_names += list(frozen_param_shapes.keys())
+
+        # handle shared params
+        shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
+
+        ds_version = state_dict.get(DS_VERSION, None)
+
+        frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
+
+        z_model_state = zero_model_state(buffers=buffers,
+                                         param_shapes=param_shapes,
+                                         shared_params=shared_params,
+                                         ds_version=ds_version,
+                                         frozen_param_shapes=frozen_param_shapes,
+                                         frozen_param_fragments=frozen_param_fragments)
+        zero_model_states.append(z_model_state)
+
+    return zero_model_states
+
+
+def parse_optim_states(files, ds_checkpoint_dir):
+
+    total_files = len(files)
+    state_dicts = []
+    for f in files:
+        state_dicts.append(torch.load(f, map_location=device))
+
+    if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
+        raise ValueError(f"{files[0]} is not a zero checkpoint")
+    zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
+    world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
+
+    # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
+    # parameters can be different from data parallelism for non-expert parameters. So we can just
+    # use the max of the partition_count to get the dp world_size.
+
+    if type(world_size) is list:
+        world_size = max(world_size)
+
+    if world_size != total_files:
+        raise ValueError(
+            f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
+            "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
+        )
+
+    # the groups are named differently in each stage
+    if zero_stage == 2:
+        fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
+    elif zero_stage == 3:
+        fp32_groups_key = FP32_FLAT_GROUPS
+    else:
+        raise ValueError(f"unknown zero stage {zero_stage}")
+
+    if zero_stage == 2:
+        fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
+    elif zero_stage == 3:
+        # if there is more than one param group, there will be multiple flattened tensors - one
+        # flattened tensor per group - for simplicity merge them into a single tensor
+        #
+        # XXX: could make the script more memory efficient for when there are multiple groups - it
+        # will require matching the sub-lists of param_shapes for each param group flattened tensor
+
+        fp32_flat_groups = [
+            torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts))
+        ]
+
+    return zero_stage, world_size, fp32_flat_groups
+
+
+def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir):
+    """
+    Returns fp32 state_dict reconstructed from ds checkpoint
+
+    Args:
+        - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
+
+    """
+    print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
+
+    optim_files = get_optim_files(ds_checkpoint_dir)
+    zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
+    print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
+
+    model_files = get_model_state_files(ds_checkpoint_dir)
+
+    zero_model_states = parse_model_states(model_files)
+    print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
+
+    if zero_stage == 2:
+        return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states)
+    elif zero_stage == 3:
+        return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states)
+
+
+def _zero2_merge_frozen_params(state_dict, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+    frozen_param_fragments = zero_model_states[0].frozen_param_fragments
+
+    if debug:
+        num_elem = sum(s.numel() for s in frozen_param_shapes.values())
+        print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        state_dict[name] = frozen_param_fragments[name]
+
+        if debug:
+            print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+
+    # Reconstruction protocol:
+    #
+    # XXX: document this
+
+    if debug:
+        for i in range(world_size):
+            for j in range(len(fp32_flat_groups[0])):
+                print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
+
+    # XXX: memory usage doubles here (zero2)
+    num_param_groups = len(fp32_flat_groups[0])
+    merged_single_partition_of_fp32_groups = []
+    for i in range(num_param_groups):
+        merged_partitions = [sd[i] for sd in fp32_flat_groups]
+        full_single_fp32_vector = torch.cat(merged_partitions, 0)
+        merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
+    avail_numel = sum(
+        [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
+
+    if debug:
+        wanted_params = sum([len(shapes) for shapes in param_shapes])
+        wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
+        # not asserting if there is a mismatch due to possible padding
+        print(f"Have {avail_numel} numels to process.")
+        print(f"Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    total_numel = 0
+    total_params = 0
+    for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
+        offset = 0
+        avail_numel = full_single_fp32_vector.numel()
+        for name, shape in shapes.items():
+
+            unpartitioned_numel = shape.numel()
+            total_numel += unpartitioned_numel
+            total_params += 1
+
+            if debug:
+                print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+            state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
+            offset += unpartitioned_numel
+
+        # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
+        # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
+        # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
+        # live optimizer object, so we are checking that the numbers are within the right range
+        align_to = 2 * world_size
+
+        def zero2_align(x):
+            return align_to * math.ceil(x / align_to)
+
+        if debug:
+            print(f"original offset={offset}, avail_numel={avail_numel}")
+
+        offset = zero2_align(offset)
+        avail_numel = zero2_align(avail_numel)
+
+        if debug:
+            print(f"aligned  offset={offset}, avail_numel={avail_numel}")
+
+        # Sanity check
+        if offset != avail_numel:
+            raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    _zero2_merge_frozen_params(state_dict, zero_model_states)
+
+    _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def zero3_partitioned_param_info(unpartitioned_numel, world_size):
+    remainder = unpartitioned_numel % world_size
+    padding_numel = (world_size - remainder) if remainder else 0
+    partitioned_numel = math.ceil(unpartitioned_numel / world_size)
+    return partitioned_numel, padding_numel
+
+
+def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    if debug:
+        for i in range(world_size):
+            num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
+            print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in zero_model_states[0].frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
+        state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+    avail_numel = fp32_flat_groups[0].numel() * world_size
+    # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
+    # param, re-consolidating each param, while dealing with padding if any
+
+    # merge list of dicts, preserving order
+    param_shapes = {k: v for d in param_shapes for k, v in d.items()}
+
+    if debug:
+        for i in range(world_size):
+            print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
+
+        wanted_params = len(param_shapes)
+        wanted_numel = sum(shape.numel() for shape in param_shapes.values())
+        # not asserting if there is a mismatch due to possible padding
+        avail_numel = fp32_flat_groups[0].numel() * world_size
+        print(f"Trainable params: Have {avail_numel} numels to process.")
+        print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    offset = 0
+    total_numel = 0
+    total_params = 0
+    for name, shape in param_shapes.items():
+
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+        total_params += 1
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+        # XXX: memory usage doubles here
+        state_dict[name] = torch.cat(
+            tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
+            0).narrow(0, 0, unpartitioned_numel).view(shape)
+        offset += partitioned_numel
+
+    offset *= world_size
+
+    # Sanity check
+    if offset != avail_numel:
+        raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
+
+    _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
+    ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
+    via a model hub.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
+
+    Returns:
+        - pytorch ``state_dict``
+
+    Note: this approach may not work if your application doesn't have sufficient free CPU memory and
+    you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
+    the checkpoint.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        # do the training and checkpoint saving
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
+        model = model.cpu() # move to cpu
+        model.load_state_dict(state_dict)
+        # submit to model hub or save the model to share with others
+
+    In this example the ``model`` will no longer be usable in the deepspeed context of the same
+    application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
+
+    """
+    if tag is None:
+        latest_path = os.path.join(checkpoint_dir, 'latest')
+        if os.path.isfile(latest_path):
+            with open(latest_path, 'r') as fd:
+                tag = fd.read().strip()
+        else:
+            raise ValueError(f"Unable to find 'latest' file at {latest_path}")
+
+    ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
+
+    if not os.path.isdir(ds_checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
+
+    return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir)
+
+
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir, output_file, tag=None):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
+    loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``output_file``: path to the pytorch fp32 state_dict output file (e.g. path/pytorch_model.bin)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+    """
+
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+    print(f"Saving fp32 state dict to {output_file}")
+    torch.save(state_dict, output_file)
+
+
+def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
+    """
+    1. Put the provided model to cpu
+    2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
+    3. Load it into the provided model
+
+    Args:
+        - ``model``: the model object to update
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+
+    Returns:
+        - ``model`: modified model
+
+    Make sure you have plenty of CPU memory available before you call this function. If you don't
+    have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
+    conveniently placed for you in the checkpoint folder.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
+        model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
+        # submit to model hub or save the model to share with others
+
+    Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
+    of the same application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    """
+    logger.info(f"Extracting fp32 weights")
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+
+    logger.info(f"Overwriting model with fp32 weights")
+    model = model.cpu()
+    model.load_state_dict(state_dict, strict=False)
+
+    return model
+
+
+if __name__ == "__main__":
+
+    parser = argparse.ArgumentParser()
+    parser.add_argument("checkpoint_dir",
+                        type=str,
+                        help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
+    parser.add_argument(
+        "output_file",
+        type=str,
+        help="path to the pytorch fp32 state_dict output file (e.g. path/checkpoint-12/pytorch_model.bin)")
+    parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
+    args = parser.parse_args()
+
+    debug = args.debug
+
+    convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir, args.output_file)